A new study claims that it is possible to utilize the genetic sequences of a person antibody to predict what pathogens these antibodies will target. The new approach, according to Immunity, has successfully differentiated between antibodies against influenza and those against COVID-19.
According to Nicholas Wu, a graduate student in biochemistry at the University of Illinois Urbana-Champaign, and Meng Yuan, a staff scientist at Scripps Research in La Jolla, California.
Scientists should be able to predict not only the virus an antibody will attack, but also which components of the spike protein used in the SARS-CoV-2 virus. Knowing this will help scientists to determine the strength of a persons immune defense, as some targets of a pathogen are more vulnerable.
Wu said the proliferation of data about antibodies against SARS-CoV-2 made this new approach possible.
Scientists have discovered about 5,000 antibodies against the flu virus in 20 years, according to the company. However, in two years, people have identified 8,000 antibodies for COVID. This is an opportunity that has never been previously to study how antibodies work and to do this type of prediction.
The researchers used antibody data from 88 published studies and 13 patents. The datasets were large enough to enable them to train their model to make predictions based on the antibodies genetic sequence.
The objective of the research was to determine if the antibodies targeting regions on the influenza virus or the SARS-CoV-2 virus were sequenced.
According to Wang, the accuracy was at least 85% in the whole.
Wu said that I was quite surprised that it worked out in such a large way.
The company is working to improve its model so that it may better determine which parts of the virus the antibodies attack.
If we can make these predictions based on the antibody sequence, then we may also be able to go back and design antibodies that attach to specific pathogens, according to Wu. This is not something we can do today, but these are some limitations for a future study."